© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194778
    Prev
    Next
    INDEX
    Explanations

    el

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    朓
    0.43
     restre
    0.43
    Odd
    0.40
     snap
    0.40
    LOTRE
    0.40
    টু
    0.39
     সেল
    0.39
     გამ
    0.39
    িনার
    0.37
     jasmine
    0.37
    POSITIVE LOGITS
    эль
    0.81
    el
    0.78
    EL
    0.77
    엘
    0.77
    él
    0.72
    els
    0.70
    ël
    0.66
    èl
    0.66
    ел
    0.65
    ель
    0.65
    Activations Density 0.006%

    No Known Activations